Repository navigation
Filtered search: single min-heap search buffer (experiment) - #457
Draft
yuejiaointel wants to merge 12 commits into
Draft
yuejiaointel wants to merge 12 commits into
yuejiaointel wants to merge 12 commits into
Conversation
Reuse the MutableBuffer valid/invalid mechanism: a FilteredValidBuilder marks an entry invalid if it is deleted or the predicate rejects its external id. New MutableVamanaIndex::search overload taking a predicate, padding rows with id -1 / +inf and returning per-query found counts. Supplement path checks the predicate before computing the distance. Orchestrator virtual appended last.
Replace the separate filtered search overload with two optional trailing arguments on MutableVamanaIndex::search (an id predicate and a per-query result count). Without a predicate the existing code path runs unchanged. check_and_supplement_search_buffer gets an optional predicate that is checked before the distance is computed. The filter predicate type is now a type-erased std::function, so FilteredValidBuilder is no longer a template. The orchestrator keeps one appended virtual that forwards to the index search.
The optional filter on MutableVamanaIndex::search now only chooses which builder the existing greedy search closure uses; both cases call the same per_thread_batch_search. FilteredValidBuilder derives from ValidBuilder. The buffer top-up in single_search applies the filter when the search closure carries one. The per-query result count out-parameter is removed (callers count non-padding ids). per_thread_batch_search now pads result rows with fewer than k entries (id size_t(-1), distance +inf) instead of reading past the end of the search buffer, and the post-search id translation skips the padding.
Give ValidBuilder an optional predicate and pass it down through internal_search_builder, greedy_search_closure and search() as optional arguments, instead of a separate builder and search path. Filtered-only checks: the supplement fallback skips failing ids, copy-out pads short rows with id -1 and the worst score, translation skips padded ids.
The orchestrator reports filtered search as unsupported for indexes whose search has no filter argument (the concurrent index), instead of failing to compile. In the filtered test, drop the unfiltered-padding section (padding is filtered-only) and add an inner-product case checking padding uses -inf.
Experiment: with a filter, MutableBuffer takes the next entry to visit from one min-heap (best on top) and stores the best valid entries in its existing vector, unsorted, tracking the worst one. greedy_search is unchanged; cleanup() sorts the results once at the end.
ValidBuilder can be given the search buffer. With a filter, it first asks the buffer whether the entry would be dropped anyway (can_skip) and, if so, returns it as invalid without looking up the external id or calling the filter. Results are unchanged.
The filter skip in ValidBuilder asks can_skip; in heap mode the worst kept entry is not back().
This reverts commit 75b59b2.
… drop" This reverts commit 4ffaf63.
The existing [filtered] dynamic index test drives heap mode end to end.
Contributor
Author
|
Closing: experiment concluded; the work continues in #456. |
…he buffer ValidBuilder is back to the main behaviour (deleted check only); the added filtered-search tests are removed.
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What this changes
MutableBufferkeeps all entries in one min-heap (best entry on top) instead of the sorted list. Differs from Filtered search: single max-heap search buffer (experiment) #454 only in heap order (Filtered search: single max-heap search buffer (experiment) #454 uses a max-heap).greedy_search, and the batch iterator are unchanged.ValidBuilderis unchanged.cleanup()sorts once at the end; top-up and copy-out are unchanged.Difference from today's search buffer (sorted list)
MutableBufferkeeps one sorted array: each insert is a binary search plus a shift. The next node to visit is a pointer to the best unvisited entry, the worst kept entry is the last valid one, and a duplicate is found by scanning the entries with an equal distance.Files
Same four files as #454; only the heap order in
MutableBufferdiffers.Tests
Existing tests.
Results
Not benchmarked yet for this version.
🤖 Generated with Claude Code